Motion-based Tracking Research Articles

Typical motion-based modelling and tracking for vehicle targets in linear road segment

In this paper, a typical motion-based modelling and tracking issue is investigated for vehicle targets in linear road segment by a variable structure multiple model (VSMM) method. Vehicle target motions in a road with multiple lanes are described by typical lane keeping and lane changing manoeuvres. To describe trajectories of typical manoeuvres, an Ornstein–Uhlenbeck process and a sine half-cycle are used to model lane keeping and lane changing motions in lateral direction, respectively. Note that starting point and length of lane changing motion are unknown in target tracking. Time-varying model sets are designed based on the current motion model with different motion parameters. A VSMM tracking frame is constructed to obtain target state estimates with time-varying model set. The effectiveness of the proposed typical motion-based tracking scheme is displayed by simulation results on road vehicle tracking.

MagicInput: Virtual Handwriting Interface Using Ubiquitous WiFi Signals

Past few years have witnessed the great potential of exploiting WiFi signals for positioning. Prior work focus on discovering the absolute locations of a radio source, and have achieved promising accuracies of tens of centimeters. However, many applications such as aerial gesture or handwriting tracking are more concerned with the detailed motion shape of the target rather than its exact locations, which require a several fold higher accuracy. To this end, we present MagicInput, a virtual handwriting interface by tracking the motion traces of a WiFi source. Based on Channel State Information (CSI), MagicInput elaborately devises an incremental motion-based tracking model by correlating the motion traces with the angle and length variations of propagation paths. The model shifts the tracking task from the transceiver view to the antenna array-oriented view, and eliminates the need for prior knowledge of anchor locations. MagicInput proposes an end-to-end pipeline for tracking refinement, by interference suppression, motion segmentation, and an integrated grasp pressure sensorbased motion instance detection. We prototype MagicInput using off-the-shelf WiFi radios, and extensive experiments attest that MagicInput can achieve the accuracy of 8.5 mm confronting diverse users and environment conditions. With ubiquitous WiFi signals, MagicInput can transform any region into an interactive handwriting interface with millimeter accuracy.

Abstract 5829: Characterizing cargoes of extracellular vesicles in promoting breast cancer growth and chemotherapy resistance

Abstract Cancer cells employ bidirectional cell communication to maintain growth and metastasis in the tumor microenvironment. One mechanism of communication that has become increasingly appreciated is the secretion of extracellular vesicles (EVs), heterogeneous multi-signal messengers that support cancer dissemination through the transfer of biomolecules such as oncoproteins and noncoding RNA species. However, little is understood about EVs in relation to chemotherapy resistance. In this study, we profiled two different breast cancer cell lines: 1) BT549 (triple negative), treated with gemcitabine and paclitaxel chemotherapy, and 2) MCF7 (estrogen receptor-positive), treated with palbociclib and fulvestrant, compared to their wild-type states. EVs were collected from these cells using tangential flow filtration and quantified with Brownian motion-based nanoparticle tracking analysis and microfluidic resistive pulse sensing, and profiling of RNA and peptide markers was completed through RT-qPCR and Western blotting, respectively. Initial data showed that representative mitochondrial ribosomal genes mt12S and MRPS14 were among the most upregulated RNAs in our drug-exposed EV samples, indicating that extracellular transfer of mitochondrial materials plays a role in cancer growth under chemotherapy stress. These findings were supported by prior genetic research at the Vasudevan laboratory, in which a set of mitochondrial ribosomal RNAs was found to be upregulated in cytosine arabinoside-induced chemoresistant acute monocytic leukemia cells, as well as by the recent discovery of mitovesicles, a novel population of EVs that originate from mitochondria. Through additional efforts to isolate further subtypes of EVs, the mechanisms by which these mitochondrial cargoes promote chemoresistant phenotypes will be uncovered. Citation Format: Harrison Ngue, Hyejin Kim, Shobha Vasudevan. Characterizing cargoes of extracellular vesicles in promoting breast cancer growth and chemotherapy resistance [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 5829.

Recognition and Tracking of Moving Objects Under Video Surveillance Using Matlab

<p>Now-a-days its becoming very important to know about any information in a digital way in order to avoid crimes and mischief activites. Conventional methods that are used now do have limited advantages we have to check for every minute information in thorough way. By using this method, we need not put effort of many hours over monitors, instead it gives the complete information about what, how and when that happened over there. This method shows how to perform automatic detection and motion-based tracking of moving objects in a video from stationary camera. Detection of motion-based tracking are important components of many computer vision applications including activity recognition, traffic monitoring and automotive safety The problem of motion based object tracking can be divided into two parts:</p> <p>[1]Detecting moving objects in each frame.</p> <p>[2]Associating the detections corresponding to the same object over time.</p> <p>For instance in a video surveillance system that aims to identify people based on their motion information, it is essential to accurately detect the moving objects and then use a robust algorithm to track them. In terms of accuracy and efficiency, the proposed method is shown to be highly accurate in determning the number of moving objects and also fast in tracking them in the scene.</p>

TEKNOLOGI MOTION-BASED TRACKING UNTUK PENGEMBANGAN APLIKASI KEAMANAN


 The surveillance camera system is widely used by the public. The surveillance camera system used is usually a CCTV camera. In general, CCTV cameras can only record video. Security monitoring or monitoring by CCTV cameras can only be effective if there are operators who see the record directly on a monitor. Actually the surveillance camera system can be programmed to give a warning sign to the user. The surveillance camera used in this study is the IP camera. The camera is a camera that can be programmed to provide a notification to the user. By implementing motion-based tracking technology on the surveillance camera system can detect movement. Kalman filter is one of the motion-based tracking methods. Kalman filters can predict the movements recorded by the IP camera. The results of this study state that the surveillance camera system can provide notification messages to users via an android device when the surveillance camera records the movement of human objects.
 

Deep Attention Models for Human Tracking Using RGBD.

Visual tracking performance has long been limited by the lack of better appearance models. These models fail either where they tend to change rapidly, like in motion-based tracking, or where accurate information of the object may not be available, like in color camouflage (where background and foreground colors are similar). This paper proposes a robust, adaptive appearance model which works accurately in situations of color camouflage, even in the presence of complex natural objects. The proposed model includes depth as an additional feature in a hierarchical modular neural framework for online object tracking. The model adapts to the confusing appearance by identifying the stable property of depth between the target and the surrounding object(s). The depth complements the existing RGB features in scenarios when RGB features fail to adapt, hence becoming unstable over a long duration of time. The parameters of the model are learned efficiently in the Deep network, which consists of three modules: (1) The spatial attention layer, which discards the majority of the background by selecting a region containing the object of interest; (2) the appearance attention layer, which extracts appearance and spatial information about the tracked object; and (3) the state estimation layer, which enables the framework to predict future object appearance and location. Three different models were trained and tested to analyze the effect of depth along with RGB information. Also, a model is proposed to utilize only depth as a standalone input for tracking purposes. The proposed models were also evaluated in real-time using KinectV2 and showed very promising results. The results of our proposed network structures and their comparison with the state-of-the-art RGB tracking model demonstrate that adding depth significantly improves the accuracy of tracking in a more challenging environment (i.e., cluttered and camouflaged environments). Furthermore, the results of depth-based models showed that depth data can provide enough information for accurate tracking, even without RGB information.

Motion-based object tracking method for safety at level crossing

This paper presents a tracking method to detect and track independently moving targets, attempting to traverse the railway, in monocular camera sequences. This method is capable of tracking the maximum number of pixels belonging to an object. The method starts by detecting and separating moving objects due to background subtraction and an energy vector-based clustering. Next, the method performs the step of tracking locally. Tracking starts by generating initial optical flow of all object pixels by propagating the optical flow of Harris corner points (calculated by Lucas–Kanade technique) using normal distribution. An iterative procedure, including Kalman filtering with adaptive parameters, color intensity difference-based optimization, and validation constraints, is then implemented to reach precise and robust optical flow estimation for the majority of the pixels of the tracked objects. Different experimental results are presented, evaluated, and discussed to show the effectiveness of the method of tracking objects that may move in complex and overlapping trajectories.

Vision-Based Turning Movement Monitoring:Count, Speed & Waiting Time Estimation

Abstract-This work presents a vision-based vehicle tracking system designed for improved intersection behavior analysis. Motion-based tracking is paired with trajectory analysis methods for accurate turning movement counts of all legs of an intersection using a single camera. Additional behavior analysis methods are implemented to estimate both speed and waiting time at intersections. Improved count accuracy is obtained through cooperation between complementary counting modules and a path reconstruction module is integrated to reconnect broken tracks of the same stationary vehicles at intersections. Experimental results show around 15% improvement in counting accuracy and different behavior of right turns were observed by speed profile and waiting time estimation. Right turns are taken more slowly than other turns and vehicle waiting times are shorter at signalized intersections since they do not always need permission from the signal. We finally show that the waiting time of right turns are directly affected by opposing flows regardless of signal phase.

February 2015: This Month in JoVE - Tracking Down Foodborne Illness, Imaging Baby Brains, and Paying Scientific Attention to Attention

Here's a look at what's coming up in the February 2015 issue of JoVE: The Journal of Visualized Experiments. In JoVE Environment we have a method for tracing outbreaks of food poisoning to insects. Everyone knows that insects can deposit diseasecausing organisms on our food. Not surprisingly, insects are important vectors of foodborne illnesses caused by pathogens like Salmonella, E. coli, and Listeria. However, it's hard to link an outbreak of food poisoning to a specific type of insect. This is because individual insects are not usually collected aseptically in environmental sampling programs. Therefore, Pava-Ripoli et al. from the U.S. Food and Drug Administration take microbial samples from individual flies under aseptic conditions and use PCR to detect specific pathogens. PCR-positive samples are then confirmed by plating on selective or differential media and through commercial biochemical assays. Using this method, public health officials can better determine how insects contribute to foodborne outbreaks. JoVE's Clinical & Translational Medicine section features cranial ultrasound-an indispensable technique for safely imaging the neonatal brain. Ecury-Goossen et al. demonstrate optimal settings that provide better imaging quality, and color Doppler techniques for visualizing intracerebral vessels. They also demonstrate how alternate acoustic windows can improve detection of brain injuries. These advances in cranial ultrasound have improved its diagnostic value-allowing timely therapeutic intervention. In JoVE Behavior we have two articles that deal with attention. One involves attentional set shifting, or the ability to direct attention to informative cues and away from irrelevant ones. Heisler et al. perform this test in mice that have been trained to dig in pots for a food reward. The test cues are different digging materials and different scents. The mice learn to pay attention to a single relevant cue to find their food. The neural circuits behind attentional set shifting are highly conserved between rodents and humans; therefore, this model can be used to preclinically evaluate cognitive deficits and potential therapies. In another article in JoVE Behavior, Yung et al. perform two well-known attention tests in an online platform. The multiple object tracking (MOT) task studies the motion-based tracking of multiple objects by the visual system, and the Useful Field of View (UFOV) Task assesses attention and processing speed of visual stimuli from a brief glance. Our authors collected data from over 1,700 participants in a Massive Online Open Course. The results were highly consistent with controlled laboratory-based measures of the same tests, showing the usefulness of behavior studies done entirely online.

Linear Acceleration Measurement Utilizing Inter-Instrument Synchronization: A Comparison between Accelerometers and Motion-Based Tracking Approaches

Where as video cameras are a reliable and established technology for the measurement of kinematic parameters, accelerometers are increasingly being employed for this type of measurement due to their ease of use, performance, and comparatively low cost. However, the majority of accelerometer-based studies involve a single channel due to the difficulty associated with synchronizing multiple accelerometer channels. The authors of this article outline a method to synchronize multiple accelerometers using a maxima detection method. Results are presented that demonstrate the effectiveness of the new synchronization method with 52 of 54 recorded data sets showing no time lag error and two tests showing an error of .04 sec. Inter-instrument and instrument-video correlations are all greater than r = .94 (p < .01), with inter-instrument precision (Root Mean Square Error; RMSE) ≈ .1ms−2, demonstrating the efficacy of the technique. In conclusion, the new technique offers a robust solution, giving further support to the movement toward wider adoption of accelerometer-based performance measurement systems in sports science.

Shadow resistant tracking using inertia constraints

In this paper, we present a new method for tracking objects with shadows. Traditional motion-based tracking schemes cannot usually distinguish the shadow from the object itself, and this results in a falsely captured object shape. If we want to utilize the object's shape information for a pattern recognition task, this poses a severe difficulty. In this paper we present a color processing scheme to project the image into an illumination invariant space such that the shadow's effect is greatly attenuated. The optical flow in this projected image together with the original image is used as a reference for object tracking so that we can extract the real object shape in the tracking process. We present a modified snake model for general video object tracking. Two new external forces are introduced into the snake equation based on the predictive contour and a new chordal string shape descriptor such that the active contour is attracted to a shape similar to the one in the previous video frame. The proposed method can deal with the problem of an object's ceasing movement temporarily, and can also avoid the problem of the snake tracking into the object interior. Global affine motion estimation is applied to mitigate the effect of camera motion, and hence the method can be applied in a general video environment. Experimental results show that the proposed method can track the real object even if there is strong shadow influence.

Feature tracking for visual servoing purposes

Object tracking is an important issue for research and application related to visual servoing and more generally for robot vision. In this paper, we address the problem of realizing visual servoing tasks on complex objects in real environments. We briefly present a set of tracking algorithms (2D features-based or motion-based tracking, 3D model-based tracking, …) that have been used for 10 years to achieve this goal.

Motion Competition: A Variational Approach to Piecewise Parametric Motion Segmentation

We present a novel variational approach for segmenting the image plane into a set of regions of parametric motion on the basis of two consecutive frames from an image sequence. Our model is based on a conditional probability for the spatio-temporal image gradient, given a particular velocity model, and on a geometric prior on the estimated motion field favoring motion boundaries of minimal length. Exploiting the Bayesian framework, we derive a cost functional which depends on parametric motion models for each of a set of regions and on the boundary separating these regions. The resulting functional can be interpreted as an extension of the Mumford-Shah functional from intensity segmentation to motion segmentation. In contrast to most alternative approaches, the problems of segmentation and motion estimation are jointly solved by continuous minimization of a single functional. Minimizing this functional with respect to its dynamic variables results in an eigenvalue problem for the motion parameters and in a gradient descent evolution for the motion discontinuity set. We propose two different representations of this motion boundary: an explicit spline-based implementation which can be applied to the motion-based tracking of a single moving object, and an implicit multiphase level set implementation which allows for the segmentation of an arbitrary number of multiply connected moving objects. Numerical results both for simulated ground truth experiments and for real-world sequences demonstrate the capacity of our approach to segment objects based exclusively on their relative motion.

EMBOT: An enhanced motion-based object tracker

The problem of tracking moving parts of image is a significant for many practical applications. There are good reasons to track a wide variety of objects, including airplanes, missiles, vehicles, people, animals, and microorganisms. There are several approaches that can be used to find out an optimal solution for this problem. Here, an enhanced motion-based tracking system is presented. The enhancements basically are: 1. Focusing attention on informative pixels in the early stages of processing rather than waiting until a motion indication is obtained. 2. Concentrating only on the region of interest that contains the moving object instead of the whole image. The effect of various factors is studied to measure the system performance and limitations. A comparison of the conventional and the proposed approach is given, and a case study is carried out in order to examine EMBOT behavior in various operational conditions.

Robust online appearance models for visual tracking

We propose a framework for learning robust, adaptive, appearance models to be used for motion-based tracking of natural objects. The model adapts to slowly changing appearance, and it maintains a natural measure of the stability of the observed image structure during tracking. By identifying stable properties of appearance, we can weight them more heavily for motion estimation, while less stable properties can be proportionately downweighted. The appearance model involves a mixture of stable image structure, learned over long time courses, along with two-frame motion information and an outlier process. An online EM-algorithm is used to adapt the appearance model parameters over time. An implementation of this approach is developed for an appearance model based on the filter responses from a steerable pyramid. This model is used in a motion-based tracking algorithm to provide robustness in the face of image outliers, such as those caused by occlusions, while adapting to natural changes in appearance such as those due to facial expressions or variations in 3D pose.

An efficient fully unsupervised video object segmentation scheme using an adaptive neural-network classifier architecture

In this paper, an unsupervised video object (VO) segmentation and tracking algorithm is proposed based on an adaptable neural-network architecture. The proposed scheme comprises: 1) a VO tracking module and 2) an initial VO estimation module. Object tracking is handled as a classification problem and implemented through an adaptive network classifier, which provides better results compared to conventional motion-based tracking algorithms. Network adaptation is accomplished through an efficient and cost effective weight updating algorithm, providing a minimum degradation of the previous network knowledge and taking into account the current content conditions. A retraining set is constructed and used for this purpose based on initial VO estimation results. Two different scenarios are investigated. The first concerns extraction of human entities in video conferencing applications, while the second exploits depth information to identify generic VOs in stereoscopic video sequences. Human face/ body detection based on Gaussian distributions is accomplished in the first scenario, while segmentation fusion is obtained using color and depth information in the second scenario. A decision mechanism is also incorporated to detect time instances for weight updating. Experimental results and comparisons indicate the good performance of the proposed scheme even in sequences with complicated content (object bending, occlusion).